submission_id: hastagaras-halu-8b-llama_7465_v1
developer_uid: Hastagaras
status: torndown
model_repo: Hastagaras/Halu-8B-Llama3-v0.35-ANJIR
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
reward_formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
timestamp: 2024-05-31T07:20:48+00:00
model_name: anjir-adapter-applied-test
model_eval_status: success
model_group: Hastagaras/Halu-8B-Llama
num_battles: 7244
num_wins: 3951
celo_rating: 1211.19
propriety_score: 1.0
propriety_total_count: 1.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: anjir-adapter-applied-test
ineligible_reason: propriety_total_count < 800
language_model: Hastagaras/Halu-8B-Llama3-v0.35-ANJIR
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-31
win_ratio: 0.5454168967421315
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-halu-8b-llama-7465-v1-mkmlizer
Waiting for job on hastagaras-halu-8b-llama-7465-v1-mkmlizer to finish
hastagaras-halu-8b-llama-7465-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-8b-llama-7465-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-halu-8b-llama-7465-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-halu-8b-llama-7465-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-halu-8b-llama-7465-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-halu-8b-llama-7465-v1-mkmlizer: ║ /___/ ║
hastagaras-halu-8b-llama-7465-v1-mkmlizer: ║ ║
hastagaras-halu-8b-llama-7465-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-halu-8b-llama-7465-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-halu-8b-llama-7465-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-halu-8b-llama-7465-v1-mkmlizer: ║ ║
hastagaras-halu-8b-llama-7465-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-halu-8b-llama-7465-v1-mkmlizer: ║ belonging to: ║
hastagaras-halu-8b-llama-7465-v1-mkmlizer: ║ ║
hastagaras-halu-8b-llama-7465-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-halu-8b-llama-7465-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-halu-8b-llama-7465-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-halu-8b-llama-7465-v1-mkmlizer: ║ ║
hastagaras-halu-8b-llama-7465-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-8b-llama-7465-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
hastagaras-halu-8b-llama-7465-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-halu-8b-llama-7465-v1-mkmlizer: Downloaded to shared memory in 28.550s
hastagaras-halu-8b-llama-7465-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-halu-8b-llama-7465-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-halu-8b-llama-7465-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 125.93it/s] Loading 0: 11%|█ | 31/291 [00:00<00:01, 147.32it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:01, 154.53it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 156.17it/s] Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 84.75it/s] Loading 0: 33%|███▎ | 95/291 [00:00<00:02, 91.77it/s] Loading 0: 39%|███▉ | 113/291 [00:01<00:01, 109.87it/s] Loading 0: 45%|████▌ | 131/291 [00:01<00:01, 124.53it/s] Loading 0: 51%|█████ | 149/291 [00:01<00:01, 134.97it/s] Loading 0: 57%|█████▋ | 167/291 [00:01<00:00, 142.30it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 97.04it/s] Loading 0: 69%|██████▉ | 202/291 [00:01<00:00, 105.07it/s] Loading 0: 76%|███████▌ | 220/291 [00:01<00:00, 119.35it/s] Loading 0: 82%|████████▏ | 238/291 [00:01<00:00, 131.65it/s] Loading 0: 88%|████████▊ | 256/291 [00:02<00:00, 141.76it/s] Loading 0: 94%|█████████▍| 274/291 [00:02<00:00, 150.29it/s] Loading 0: 100%|██████████| 291/291 [00:07<00:00, 10.54it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-halu-8b-llama-7465-v1-mkmlizer: quantized model in 22.617s
hastagaras-halu-8b-llama-7465-v1-mkmlizer: Processed model Hastagaras/Halu-8B-Llama3-v0.35-ANJIR in 53.708s
hastagaras-halu-8b-llama-7465-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-halu-8b-llama-7465-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-8b-llama-7465-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-8b-llama-7465-v1
hastagaras-halu-8b-llama-7465-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-7465-v1/config.json
hastagaras-halu-8b-llama-7465-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-7465-v1/special_tokens_map.json
hastagaras-halu-8b-llama-7465-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-7465-v1/tokenizer_config.json
hastagaras-halu-8b-llama-7465-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-7465-v1/tokenizer.json
hastagaras-halu-8b-llama-7465-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-8b-llama-7465-v1/flywheel_model.0.safetensors
hastagaras-halu-8b-llama-7465-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-8b-llama-7465-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:913: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
hastagaras-halu-8b-llama-7465-v1-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-7465-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:757: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
hastagaras-halu-8b-llama-7465-v1-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-7465-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:468: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
hastagaras-halu-8b-llama-7465-v1-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-7465-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
hastagaras-halu-8b-llama-7465-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-halu-8b-llama-7465-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-halu-8b-llama-7465-v1-mkmlizer: Saving duration: 0.395s
hastagaras-halu-8b-llama-7465-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.959s
hastagaras-halu-8b-llama-7465-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-halu-8b-llama-7465-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-halu-8b-llama-7465-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-halu-8b-llama-7465-v1_reward
hastagaras-halu-8b-llama-7465-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-7465-v1_reward/special_tokens_map.json
hastagaras-halu-8b-llama-7465-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-7465-v1_reward/tokenizer_config.json
hastagaras-halu-8b-llama-7465-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-halu-8b-llama-7465-v1_reward/merges.txt
hastagaras-halu-8b-llama-7465-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-7465-v1_reward/config.json
hastagaras-halu-8b-llama-7465-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-7465-v1_reward/vocab.json
hastagaras-halu-8b-llama-7465-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-7465-v1_reward/tokenizer.json
hastagaras-halu-8b-llama-7465-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-halu-8b-llama-7465-v1_reward/reward.tensors
Job hastagaras-halu-8b-llama-7465-v1-mkmlizer completed after 73.08s with status: succeeded
Stopping job with name hastagaras-halu-8b-llama-7465-v1-mkmlizer
Pipeline stage MKMLizer completed in 73.43s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-8b-llama-7465-v1
Waiting for inference service hastagaras-halu-8b-llama-7465-v1 to be ready
Failed to get response for submission blend_larer_2024-05-23: ('http://mistralai-mixtral-8x7b-3473-v33-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'dial tcp 10.147.59.220:8012: connect: connection refused\n')
Inference service hastagaras-halu-8b-llama-7465-v1 ready after 30.15821385383606s
Pipeline stage ISVCDeployer completed in 35.70s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.193225622177124s
Received healthy response to inference request in 1.3329298496246338s
Received healthy response to inference request in 1.3166930675506592s
Received healthy response to inference request in 1.2825160026550293s
Received healthy response to inference request in 1.2217979431152344s
5 requests
0 failed requests
5th percentile: 1.2339415550231934
10th percentile: 1.2460851669311523
20th percentile: 1.2703723907470703
30th percentile: 1.2893514156341552
40th percentile: 1.3030222415924073
50th percentile: 1.3166930675506592
60th percentile: 1.323187780380249
70th percentile: 1.3296824932098388
80th percentile: 1.504989004135132
90th percentile: 1.849107313156128
95th percentile: 2.021166467666626
99th percentile: 2.1588137912750245
mean time: 1.469432497024536
Pipeline stage StressChecker completed in 8.17s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.04s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-halu-8b-llama_7465_v1 status is now deployed due to DeploymentManager action
hastagaras-halu-8b-llama_7465_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-halu-8b-llama_7465_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-halu-8b-llama-7465-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.24s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-halu-8b-llama-7465-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-7465-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-7465-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-7465-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-7465-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-halu-8b-llama-7465-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-7465-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-7465-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-7465-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-7465-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-7465-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-7465-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.95s
hastagaras-halu-8b-llama_7465_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics